Artificial intelligence. Freefall. Dzhimsher Chelidze

term AGI and its brief description.” Below I will give the answers of several LLMs in the original spelling.

      YandexGPT 2: “AGI (Artificial General Intelligence) is a general-purpose artificial intelligence that can solve a variety of tasks typical of the human mind. AGI has the flexibility and adaptability of the human brain and can learn independently”.”

      YandexGPT 3 Pro: “AGI (Artificial General Intelligence) is a concept for creating artificial intelligence that will be able to solve a wide range of tasks at the level of human intelligence. This is the next step in the development of artificial intelligence after highly specialized systems, such as speech recognition or computer vision systems.”

      YandexGPT 4 Pro RC: “AGI (Artificial General Intelligence) is artificial general intelligence, which is a hypothetical form of AI that can understand and solve problems at the same level as humans. AGI can learn, adapt, and make decisions in various fields, such as science, art, and social interactions.

      Unlike specialized AI systems that are designed to perform specific tasks, AGI strives for versatility and the ability to solve a wide range of problems. However, creating an AGI remains a complex task that requires significant research and development in machine learning, neural networks, and other technologies.”

      Giga Chat: “AGI (Artificial General Intelligence) – general artificial intelligence. This is the concept of creating an intelligent machine that can solve any intellectual tasks in the same way as a human does, and perhaps better than him.”

      ChatGPT4: “AGI stands for Artificial General Intelligence (Automated General Intelligence), which is a type of artificial intelligence that can perform a wide range of intelligent tasks at the human level or even surpass it. This is in contrast to highly specialized AI, which is designed for specific tasks. Building an AGI is one of the main goals of AI research and companies like Open AI. The time to reach AGI is the subject of discussions withered researchers and experts.”

      However, the original query also has a significant impact on the result.

      I will also give you some examples of the Q & A bundle for LLM YandexGPT 3 Pro.

      Question 1: “Hi. What is strong AI or AGI?”

      Answer 1: “Hi! Strong AI, also known as AGI (Artificial General Intelligence), is the concept of creating artificial intelligence that can perform any intellectual tasks available to humans, but not necessarily in the same way as a human does. Unlike weak AI, which is designed to perform specific tasks, strong AI tends to mimic human intelligence in general, including analytical thinking and learning abilities”.”

      Question 2: “AGI decryption”.

      Answer 2: “AGI – Artificial General Intelligence) is the concept of creating artificial intelligence that will be able to solve a wide range of tasks at the level of human intelligence”.”

      Question 3: “What is the explanation of the term AGI and its description?”

      Answer 3: “AGI (Artificial General Intelligence) is a strong general – level artificial intelligence capable of thinking and acting like a human. They can make independent conclusions, learn, and possibly become self-aware at some point in time. Unlike Narrow AI, AGI is the entire brain capable of solving a set of tasks”.”

      As you can see, a lot depends on the request. And this is one of the key limitations of generative AI (GII), but we’ll talk about it in the next chapter.

      Now I will give the definition that, in my opinion, most accurately defines its essence.

      Strong or general AI (AGI) is an AI that can navigate changing conditions, model and predict the development of a situation. And if the situation goes beyond the standard algorithms, then find a solution yourself. For example, to solve the problem “go to university” and learn the rules of the game of checkers, and instead of chess, start playing checkers.

      What qualities should such an AI have?

      Thinking is the use of methods such as deduction, induction, association, etc., which are aimed at extracting facts from information, their presentation (preservation). This will make it possible to solve problems more accurately in conditions of uncertainty

      Memory is the use of various types of memory (short-term, long-term). That is, the tasks should be solved taking into account the accumulated experience. Now, if you chat with ChatGPT 4, you will see that the algorithm has a small short-term memory and after a while forgets where it all started. In general, in my opinion, the issue of memory and the “massiveness” of AI models will be a key limitation in the development of AI. More on this below.

      Planning – tactical and strategic. Yes, there are already studies that claim that AI can plan its actions and even deceive a person to achieve its goals. But now it’s still only in its infancy. The deeper the planning goes, especially in conditions of uncertainty, the more capacity is needed. After all, it’s one thing to plan a game of chess 3—6 steps deep, where all the rules are clear, and another in a situation of uncertainty.

      Training – simulating the actions of another object and learning through experimentation. Now he is learning from large amounts of data, but he does not model or conduct experiments himself. Although we do not fully understand how the same Chat GPT works, and this is one of the main problems, learning requires the formation of long-term memory and complex relationships. And this, as we understand it, is a problem for AI.

      And now no one has such a strong AI right now. And the statement about the imminent (in the2024—2028horizon) appearance of a strong AI, in my opinion, is erroneous or speculative. Although maybe, I have too limited knowledge…

      Yes, ChatGPT from Open AI and other LLMs can generate text / illustrations / videos through query analysis and big data processing. But they only broadcast what the creators gave them for training. They search for the most appropriate combinations of words and sentences, words and images for the query, and in general, associative combinations. But don’t be under any illusions, this is just mathematics and statistics. And in their answers, there are a lot of “marriage” and “hallucinations”. They are not yet ready for real interaction with the world.

      Here is a simple LLM-based example.

      I – come from a project management background, and as part of my work, I decided to write an article about why Agile is not a universal approach to project management, and why, if applied correctly, any company and team should move closer to hybrid or cascading approaches.

      My assistants in writing text were all the same ChatGPT, GigaChat, YandexGPT and AI Search.

      I formulated a simple request: “Write a post about why Agile is infinitely wrong to apply. Emphasize that conducting retrospectives should lead away from the situation of uncertainty to the situation of complex ordered or simple ordered systems.”

      ChatGPT4’s answer: “Agile is an approach to software development that is based on iterative and incremental product development, collaboration between self-organizing teams, and continuous process improvement. One of the key principles of Agile is to conduct regular retrospectives, i.e., sessions where the team analyzes its work, identifies problems and finds ways to solve them.

      Retrospectives are a powerful tool for improving the efficiency and quality of work, but only if they are conducted correctly. Unfortunately, many teams make the mistake of applying Agile indefinitely, without taking into account the context and changes in the environment. This leads to the fact that retrospectives become useless, boring and demotivating.

      To avoid this, you need to understand that Agile is not a universal solution for every situation. Depending on the degree of uncertainty and complexity of the project,